Data visualisation


Registration number: 19BCE1717
Faculty: Prof. Parvathi R
Slot: L55 + L56
Course code: CSE3020

Instructions:

Explore the lattice package in R using the HSB2 dataset and the builtin MTCars dataset. Run the code given in class

Sections:

PART 1: HSB2 dataset

Import required package and dataset:
library(lattice)
df = read.csv("hsb2.csv")
head(df, 5)
##    id female race ses schtyp prog read write math science socst
## 1  70      0    4   1      1    1   57    52   41      47    57
## 2 121      1    4   2      1    3   68    59   53      63    61
## 3  86      0    4   3      1    1   44    33   54      58    31
## 4 141      0    4   3      1    3   63    44   47      53    56
## 5 172      0    4   2      1    2   47    52   57      53    61
Create factors with value labels
ses.f <-factor(df$ses,levels=c(1,2,3),
labels=c("ses_1","ses_2","ses_3"))

prog.f <-factor(df$prog,levels=c(1,2,3),
labels=c("prog_1","prog_2","prog_3"))
xy Scatter plot
xyplot(df$read~df$write)

Scatterplots for each combination of two factors
xyplot(df$read~df$write|ses.f*prog.f,
main="Scatterplots by Cylinders and Gears",
ylab="Miles per Gallon", xlab="Car Weight")

XYplot
xyplot(read~write,
       data = df,
       type = c("p", "r"),
       main = "Relation between Read and Write",
       xlab = "Read Score",
       ylab = "Write Score")

Multivariate xy scatter plot with customizations
xyplot(df$read~df$write | ses.f,
       data = df,
       type = c("p", "r"),
       groups = ses.f,
       main = "Relation between Read and Write",
       xlab = "Read Score",
       ylab = "Write Score")

Kernel density plot
densityplot(~df$read,
main="Density Plot",
xlab="Read score")

Kernel density plots by factor level
densityplot(~df$read|ses.f, data = df,
main="Read Score by SES",
xlab="Read Score")

Kernel density plots by factor level (alternate layout)
densityplot(~df$read|ses.f,
main="Density Plot by SES",
xlab="Read score",
layout=c(1,3))

Kernel Density Plot together for all factors without points
densityplot(~df$read,
groups = ses.f,
plot.points = FALSE,
main = "Kernel density plot over SES",
xlab = "Read score")

Boxplot
bwplot(prog.f ~ df$read | ses.f,
xlab = "SES",
ylab = "Prog",
Main = "Prog given by SES")

Boxplots for each combination of two factors
bwplot(ses.f~df$read|prog.f,
ylab="SES", xlab="PROG",
main ="SES and Prog")

Boxplot associated with multiple variables and alternate layout
bwplot(prog.f ~ df$read |ses.f,
xlab = "READ score",
ylab = "PROG",
Main = "SES and read score",
layout = c(1, 3))

3D plot
# 3 d plot
cloud(df$socst~df$science*df$math,main = "3D scatterplot")

3d scatterplot by factor level
cloud(df$science~df$math*df$socst|ses.f,
main="3D Scatterplot by SES")

Dotplot for each combination of two factors
dotplot(ses.f~df$read|prog.f,
main="Dotplot Plot by SES and prog",
xlab="Read score")

Scatterplot matrix
splom(df[c(1,3,4,5,6)],
main="hsb2 Data")

bwplot(prog.f ~ df$read | ses.f,
data = df,
xlab = "Read score",
ylab = "PROG",
Main = "PROG and SES",
panel = panel.violin)

Contour plot
data <- dimnames(volcano)
contour(x=volcano, xlab = "Row", ylab = "Column") # Contour plot for volcano dataset

filled.contour(volcano)

filled.contour(volcano,color.palette = terrain.colors)

The same is repeated using the MTCars dataset below


PART 2: MTCars datset

Import necessary package and datset:
library(lattice) # already imported from part 1
attach(mtcars)
mtcars
##                      mpg cyl  disp  hp drat    wt  qsec vs am gear carb
## Mazda RX4           21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4
## Mazda RX4 Wag       21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4
## Datsun 710          22.8   4 108.0  93 3.85 2.320 18.61  1  1    4    1
## Hornet 4 Drive      21.4   6 258.0 110 3.08 3.215 19.44  1  0    3    1
## Hornet Sportabout   18.7   8 360.0 175 3.15 3.440 17.02  0  0    3    2
## Valiant             18.1   6 225.0 105 2.76 3.460 20.22  1  0    3    1
## Duster 360          14.3   8 360.0 245 3.21 3.570 15.84  0  0    3    4
## Merc 240D           24.4   4 146.7  62 3.69 3.190 20.00  1  0    4    2
## Merc 230            22.8   4 140.8  95 3.92 3.150 22.90  1  0    4    2
## Merc 280            19.2   6 167.6 123 3.92 3.440 18.30  1  0    4    4
## Merc 280C           17.8   6 167.6 123 3.92 3.440 18.90  1  0    4    4
## Merc 450SE          16.4   8 275.8 180 3.07 4.070 17.40  0  0    3    3
## Merc 450SL          17.3   8 275.8 180 3.07 3.730 17.60  0  0    3    3
## Merc 450SLC         15.2   8 275.8 180 3.07 3.780 18.00  0  0    3    3
## Cadillac Fleetwood  10.4   8 472.0 205 2.93 5.250 17.98  0  0    3    4
## Lincoln Continental 10.4   8 460.0 215 3.00 5.424 17.82  0  0    3    4
## Chrysler Imperial   14.7   8 440.0 230 3.23 5.345 17.42  0  0    3    4
## Fiat 128            32.4   4  78.7  66 4.08 2.200 19.47  1  1    4    1
## Honda Civic         30.4   4  75.7  52 4.93 1.615 18.52  1  1    4    2
## Toyota Corolla      33.9   4  71.1  65 4.22 1.835 19.90  1  1    4    1
## Toyota Corona       21.5   4 120.1  97 3.70 2.465 20.01  1  0    3    1
## Dodge Challenger    15.5   8 318.0 150 2.76 3.520 16.87  0  0    3    2
## AMC Javelin         15.2   8 304.0 150 3.15 3.435 17.30  0  0    3    2
## Camaro Z28          13.3   8 350.0 245 3.73 3.840 15.41  0  0    3    4
## Pontiac Firebird    19.2   8 400.0 175 3.08 3.845 17.05  0  0    3    2
## Fiat X1-9           27.3   4  79.0  66 4.08 1.935 18.90  1  1    4    1
## Porsche 914-2       26.0   4 120.3  91 4.43 2.140 16.70  0  1    5    2
## Lotus Europa        30.4   4  95.1 113 3.77 1.513 16.90  1  1    5    2
## Ford Pantera L      15.8   8 351.0 264 4.22 3.170 14.50  0  1    5    4
## Ferrari Dino        19.7   6 145.0 175 3.62 2.770 15.50  0  1    5    6
## Maserati Bora       15.0   8 301.0 335 3.54 3.570 14.60  0  1    5    8
## Volvo 142E          21.4   4 121.0 109 4.11 2.780 18.60  1  1    4    2
Create factors with value labels
gear.f<-factor(gear,levels=c(3,4,5),
labels=c("3gears","4gears","5gears"))
cyl.f <-factor(cyl,levels=c(4,6,8),
labels=c("4cyl","6cyl","8cyl"))
xy Scatter plot
xyplot(mpg~wt)

Scatterplots for each combination of two factors
xyplot(mpg~wt|cyl.f*gear.f,
main="Scatterplots by Cylinders and Gears",
ylab="Miles per Gallon", xlab="Car Weight")

XYplot
#XYplot 1
xyplot(mpg~wt,
data = mtcars,
type = c("p", "r"),
main = "Relation between wt and mpg",
xlab = "Weight in lbs",
ylab = "Miles/Gallon (US)")

#XYplot 2
xyplot(mpg~wt | cyl.f,
type = c("p", "r"),
groups = cyl.f,
main = "Relation between wt and mpg over cylinders",
xlab = "Weight in lbs",
ylab = "Miles/Gallon (US)")

Multivariate xy scatter plot with customizations
xyplot(mpg~wt | cyl.f,
type = c("p", "r"),
groups = cyl.f,
main = "Relation between wt and mpg over cylinders",
xlab = "Weight in lbs",
ylab = "Miles/Gallon (US)")

Kernel density plot
densityplot(~mpg,
main="Density Plot",
xlab="Miles per Gallon")

Kernel density plots by factor level
densityplot(~mpg|cyl.f,
main="Density Plot by Number of Cylinders",
xlab="Miles per Gallon")

Kernel density plots by factor level (alternate layout)
densityplot(~mpg|cyl.f,
main="Density Plot by Numer of Cylinders",
xlab="Miles per Gallon",
layout=c(1,3))

Kernel Density Plot together for all factors without points
densityplot(~mpg,
groups = gear.f,
plot.points = FALSE,
main = "Kernel density plot over number of gears",
xlab = "Miles Per Gallon (US)")

Boxplot
bwplot(gear.f ~ mpg | cyl.f,
xlab = "Miles per Gallon (US)",
ylab = "No of Gears",
Main = "Mileage by no. of gears and cylinders")

Boxplots for each combination of two factors
bwplot(cyl.f~mpg|gear.f,
ylab="Cylinders", xlab="Miles per Gallon",
main ="Mileage by Cylinders and Gears")

Boxplot associated with multiple variables and alternate layout
bwplot(gear.f ~ mpg |cyl.f,
xlab = "Miles per Gallon (US)",
ylab = "No of Gears",
Main = "Mileage by no. of gears and cylinders",
layout = c(1, 3))

3D plot
# 3 d plot
cloud(mpg~wt*qsec,main = "3D scatterplot")

3d scatterplot by factor level
cloud(mpg~wt*qsec|cyl.f,
main="3D Scatterplot by Cylinders")

Dotplot for each combination of two factors
dotplot(cyl.f~mpg|gear.f,
main="Dotplot Plot by Number of Gears and Cylinders",
xlab="Miles Per Gallon")

Scatterplot matrix
splom(mtcars[c(1,3,4,5,6)],
main="MTCARS Data")

bwplot(gear.f ~ mpg | cyl.f,
data = mtcars,
xlab = "Miles per Gallon (US)",
ylab = "No of Gears",
Main = "Mileage by no. of gears and cylinders",
panel = panel.violin)

Contour plot
data <- dimnames(volcano)
contour(x=volcano, xlab = "Row", ylab = "Column") # Contour plot for volcano dataset

filled.contour(volcano)

filled.contour(volcano,color.palette = terrain.colors)